Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Violence and body mutilation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hük
    -0.07
     hük
    -0.07
    ць
    -0.07
     />}↵
    -0.07
     stumbling
    -0.07
    оля
    -0.06
     Paras
    -0.06
    /login
    -0.06
    Administr
    -0.06
    elic
    -0.06
    POSITIVE LOGITS
    {l
    0.07
    CLS
    0.06
    شر
    0.06
    motion
    0.06
    Raster
    0.06
     mutually
    0.06
     inflicted
    0.06
    .GetSize
    0.06
    receipt
    0.06
    Оп
    0.06
    Act Density 0.019%

    No Known Activations